
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")


df=pd.read_csv(r"D:\JAIMIN\Data Analysis\Python\Cognifyz Technologies\Dataset .csv")

df


Top_3_Cuisines =df['Cuisines'].value_counts().nlargest(3).index.tolist()


print("The Top 3 Cusinies are: ")
for index, Cuisines in enumerate(Top_3_Cuisines, 1):
    print(f"{index}.{Cuisines}")

The Top 3 Cusinies are: 
1.North Indian
2.North Indian, Chinese
3.Chinese


percentage_cuisine = (df['Cuisines'].value_counts(normalize=True)*100).loc[Top_3_Cuisines]
print("\n Percentage of Restaurants that serve each of the top cuisines:")
for Cuisines, percentage in percentage_cuisine.items():
    print(f" {Cuisines}: {percentage: 2f}%")

 Percentage of Restaurants that serve each of the top cuisines:
 North Indian:  9.809264%
 North Indian, Chinese:  5.355271%
 Chinese:  3.709914%


Highest_No_Restaurants = df['City'].value_counts().idxmax()
print(f" The City with the Highest Number of Restaurants is: {Highest_No_Restaurants}")

 The City with the Highest Number of Restaurants is: New Delhi


Average_Rating_Restaurants = df.groupby('City')['Aggregate rating'].mean()
City_Highest_Average_Rating = Average_Rating_Restaurants.idxmax()
Highest_Average_Rating = Average_Rating_Restaurants.max()
print(f" \n The Average Rating for Restaurants in Each City is: {Highest_Average_Rating: .2f}")
print(f" \n The City with the Highest Average Rating is: {City_Highest_Average_Rating}")

 
 The Average Rating for Restaurants in Each City is:  4.90
 
 The City with the Highest Average Rating is: Inner City


# Bar Chart
colors = ['green', 'orange', 'red', 'blue']
plt.figure(figsize=(10,7))
df['Price range'].value_counts().sort_index().plot(kind="bar", color=colors)
plt.title(" Distribution of price range among the restaurants")
plt.xlabel('Price Range')
plt.ylabel('Number of Restaurants')
plt.xticks(rotation=0)
plt.show()


sns.set_style('dark')
ax = sns.countplot(x = 'Price range', data=df, palette = 'RdBu_r')
for bars in ax.containers: 
    ax.bar_label(bars)


Price_Range_Percentage_Restaurants = (df['Price range']. value_counts(normalize=True)*100).sort_index()
print(" \n Percentage of Restuarants in Each Price Range Category is:0")
for price_range, percentage in Price_Range_Percentage_Restaurants.items():
    print(f" Price range {price_range}: {percentage: .2f}%")

 
 Percentage of Restuarants in Each Price Range Category is:0
 Price range 1:  46.53%
 Price range 2:  32.59%
 Price range 3:  14.74%
 Price range 4:  6.14%


Online_Delivery_Percentage_Restaurants = (df['Has Online delivery'].value_counts(normalize=True)*100).get('Yes',0)
print(f" Percentage of Restaurants that offer Online delivery: {Online_Delivery_Percentage_Restaurants: .2f}%")

 Percentage of Restaurants that offer Online delivery:  25.66%


Average_Rating_With_Online_Delivery = df[df['Has Online delivery'] == 'Yes']['Aggregate rating'].mean()
Average_Rating_Without_Online_Delivery = df[df['Has Online delivery'] == 'No']['Aggregate rating'].mean()
print(f" \n Average Rating of Restaurants with Online Delivery: {Average_Rating_With_Online_Delivery:.2f}")
print(f" \n Average Rating of Restaurants without Online Delivery: {Average_Rating_Without_Online_Delivery: .2f}")

 
 Average Rating of Restaurants with Online Delivery: 3.25
 
 Average Rating of Restaurants without Online Delivery:  2.47


Rating_Counts = df['Aggregate rating'].value_counts().sort_index(ascending=False)
Most_Common_Rating_Range = Rating_Counts.idxmax()
print(f"Most common Rating Range is: {Most_Common_Rating_Range}")

Most common Rating Range is: 0.0


Average_No_Of_Votes = df['Votes'].mean()
print(f" \n Average Number of Votes Received by Restaurants: {Average_No_Of_Votes: .2f}")

 
 Average Number of Votes Received by Restaurants:  156.91


# Unique Combinations for cuisines
unique_combinations = df['Cuisines'].str.split(',').explode().unique()


# Combination Counts
combination_counts = pd.DataFrame(columns=['Combination','Count', 'Average Rating'])


# Calculate Counts and Average Ratings
for combination in unique_combinations:
    combination_filter = df['Cuisines'].apply(lambda x: str(x).lower().find(str(combination).lower()) != -1 if pd.notna(x) else False)
    combination_count = combination_filter.sum()
    average_rating = df.loc[combination_filter, 'Aggregate rating'].mean()
    new_row = pd.DataFrame([{'Combination': combination, 'Count': combination_count, 'Average Rating': average_rating}])
    combination_counts = pd.concat([combination_counts, new_row], ignore_index=True)
    
# Sorting DataFrame
combination_counts = combination_counts.sort_values(by='Count', ascending=False)

print("Most common Cuisine Combinations:")
print(combination_counts[['Combination', 'Count']])
print("\n Average Ratings for Cuisine Combinations:")
print(combination_counts[['Combination', 'Average Rating']])

Most common Cuisine Combinations:
        Combination Count
54           Indian  4259
7            Indian  4220
144    North Indian  3960
10          Chinese  2733
27        Fast Food  1987
..              ...   ...
218       Peranakan     1
203  Cuisine Varies     1
202         Malwani     1
249   World Cuisine     1
63              NaN     0

[250 rows x 2 columns]

 Average Ratings for Cuisine Combinations:
        Combination  Average Rating
54           Indian        2.525053
7            Indian        2.510972
144    North Indian        2.510455
10          Chinese        2.620234
27        Fast Food        2.563966
..              ...             ...
218       Peranakan        4.000000
203  Cuisine Varies        0.000000
202         Malwani        3.500000
249   World Cuisine        3.700000
63              NaN             NaN

[250 rows x 2 columns]


pip install folium

Requirement already satisfied: folium in d:\anaconda\anaconda3\lib\site-packages (0.17.0)
Requirement already satisfied: branca>=0.6.0 in d:\anaconda\anaconda3\lib\site-packages (from folium) (0.7.2)
Requirement already satisfied: jinja2>=2.9 in d:\anaconda\anaconda3\lib\site-packages (from folium) (3.1.2)
Requirement already satisfied: numpy in d:\anaconda\anaconda3\lib\site-packages (from folium) (1.24.3)
Requirement already satisfied: requests in d:\anaconda\anaconda3\lib\site-packages (from folium) (2.31.0)
Requirement already satisfied: xyzservices in d:\anaconda\anaconda3\lib\site-packages (from folium) (2022.9.0)
Requirement already satisfied: MarkupSafe>=2.0 in d:\anaconda\anaconda3\lib\site-packages (from jinja2>=2.9->folium) (2.1.1)
Requirement already satisfied: charset-normalizer<4,>=2 in d:\anaconda\anaconda3\lib\site-packages (from requests->folium) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in d:\anaconda\anaconda3\lib\site-packages (from requests->folium) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in d:\anaconda\anaconda3\lib\site-packages (from requests->folium) (1.26.16)
Requirement already satisfied: certifi>=2017.4.17 in d:\anaconda\anaconda3\lib\site-packages (from requests->folium) (2023.7.22)
Note: you may need to restart the kernel to use updated packages.


import folium
from folium.plugins import MarkerCluster


import folium
map_center = folium.Map(location=[df['Latitude'].mean(), df['Longitude'].mean()], zoom_start=10)

for index, row in df.iterrows():
    latitude = row['Latitude']
    longitude = row['Longitude']
    location_name = row['Restaurant Name']
    marker = folium.Marker([latitude, longitude], tooltip=location_name)
    marker.add_to(map_center)

# Save the map as an HTML file or display it
map_center.save("map.html")
#map_center


import plotly.express as px
fig = px.scatter(df, x='Latitude', y='Longitude', text='Restaurant Name',
                 title='Scatter Plot of Latitude vs. Longitude with Restaurant Names')

fig.update_traces(marker=dict(size=8, opacity=0.7, line=dict(width=0)))

fig.update_traces(textposition='top center')
fig.show()


from scipy.cluster.hierarchy import linkage
from sklearn.preprocessing import StandardScaler
X = df[['Latitude', 'Longitude']]

scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

#hierarchical clustering
linked = linkage(X_scaled, method='ward')
plt.figure(figsize=(12, 8))
sns.clustermap(X_scaled, method='ward', cmap='viridis', figsize=(10, 8))

plt.title('Agglomerative Hierarchical Clustering')
plt.show()

<Figure size 1200x800 with 0 Axes>


import folium
from folium.plugins import MarkerCluster
import pandas as pd


# Filter out rows with missing latitude or longitude values
df= df.dropna(subset=['Latitude', 'Longitude'])
df = pd.DataFrame(df)


# Create a map
average_latitude = df['Latitude'].mean()
average_longitude = df['Longitude'].mean()
restaurant_map = folium.Map(location = [average_latitude, average_longitude], zoom_start = 12)
restaurant_map = folium.Map(location=[22.3072, 73.1812], zoom_start=13)


# Create MarkerCluster
marker_cluster = MarkerCluster().add_to(restaurant_map)


# Add Markers for each restaurant
for index, row in df.iterrows():
    folium.Marker(location=[row['Latitude'], row['Longitude']], popup=row['Restaurant Name']).add_to(marker_cluster)


# Save the map as HTML
restaurant_map.save('restaurant_map.html')
restaurant_map


restaurant_chains = df['Restaurant Name']. value_counts()


chains = restaurant_chains[restaurant_chains > 1].index


chain_df = df[df['Restaurant Name'].isin(chains)].copy()


chain_analysis = chain_df.groupby('Restaurant Name').agg({'Aggregate rating': 'mean', 'Votes': "sum", 'Average Cost for two': 'mean'}).sort_values(by='Votes',ascending=False)
print("Restaurant Chains Analysis:")
print(chain_analysis)

Restaurant Chains Analysis:
                           Aggregate rating  Votes  Average Cost for two
Restaurant Name                                                         
Barbeque Nation                    4.353846  28142           1498.076923
AB's - Absolute Barbecues          4.825000  13400           1500.000000
Big Chill                          4.475000  10853           1500.000000
Farzi Cafe                         4.366667  10098           1516.666667
Truffles                           3.950000   9682            550.000000
...                                     ...    ...                   ...
Bikaner Misthan Bhandar            0.000000      0            250.000000
Aap Ki Khatir                      0.000000      0            400.000000
Street Cafe                        0.000000      0            300.000000
Jyoti Sweets                       0.000000      0            200.000000
Firangi Bake                       0.000000      0            300.000000

[734 rows x 3 columns]


chain = df.groupby('Restaurant Name').agg({'Aggregate rating':'mean', 'Votes':'sum'})
chain = chain.sort_values(by='Aggregate rating', ascending=False)
top_chain = chain.head(10)

print('Top 10 Restaurant Chains:')
print(top_chain)

custom_palette = sns.color_palette("Blues_d", n_colors=len(top_chain))

plt.figure(figsize=(12, 6))

plt.subplot(1, 2, 1)
sns.barplot(x=top_chain['Aggregate rating'], y=top_chain.index, palette=custom_palette)
plt.xlabel('Average Rating')
plt.title('Average Rating of Top Chains')

plt.subplot(1, 2, 2)
sns.barplot(x=top_chain['Votes'], y=top_chain.index, palette=custom_palette)
plt.xlabel('Total Votes (Popularity)')
plt.title('Popularity of Top Chains')

plt.tight_layout()
plt.show()

Top 10 Restaurant Chains:
                                Aggregate rating  Votes
Restaurant Name                                        
Restaurant Mosaic @ The Orient               4.9     85
Ministry of Crab                             4.9    203
Miann                                        4.9    281
Shorts Burger and Shine                      4.9    820
Milse                                        4.9    754
Yellow Dog Eats                              4.9   1252
Duck & Waffle                                4.9    706
Gaga Manjero                                 4.9     95
Mirchi And Mime                              4.9   3244
McGuire's Irish Pub & Brewery                4.9   2238


text_reviews = df['Rating text'].value_counts()
print("Rating text are as follows: ")
print(text_reviews)

sentiment_mapping = {
    'Good': 'Positive',
    'Very Good': 'Positive',
    'Excellent': 'Positive',
    'Poor': 'Negative',
    'Not rated': 'Neutral',
    'Average': 'Neutral',
}

custom_palette = sns.color_palette("husl", len(text_reviews))
df['Sentiment'] = df['Rating text'].map(sentiment_mapping)
plt.figure(figsize=(10, 6))
bars = plt.bar(text_reviews.index, text_reviews.values, color=custom_palette)

plt.xlabel('Rating Text')
plt.ylabel('Count')
plt.title('Distribution of Rating Text')
plt.xticks(rotation=45)
plt.grid(axis='y', linestyle='--', alpha=0.6)
plt.ylim(0, text_reviews.max() + 100)

for bar, count in zip(bars, text_reviews.values):
    plt.text(bar.get_x() + bar.get_width() / 2, count + 5, str(count), ha='center', va='bottom')

plt.show()

df['Sentiment']

Rating text are as follows: 
Rating text
Average      3737
Not rated    2148
Good         2100
Very Good    1079
Excellent     301
Poor          186
Name: count, dtype: int64

0       Positive
1       Positive
2       Positive
3       Positive
4       Positive
          ...   
9546    Positive
9547    Positive
9548    Positive
9549    Positive
9550    Positive
Name: Sentiment, Length: 9551, dtype: object


df['Review Length'] = df['Rating text'].str.len()
df['Review Length']
average_review_length = df.groupby('Sentiment')['Review Length'].mean()

average_review_length.plot(kind='bar')
plt.xlabel('Sentiment')
plt.ylabel('Average Review Length')
plt.title('Relationship Between Review Length and Sentiment')
plt.xticks(rotation=45)
plt.show()

print("Average Review Length by Sentiment:")
print(average_review_length)

Average Review Length by Sentiment:
Sentiment
Negative    4.000000
Neutral     7.729992
Positive    5.982759
Name: Review Length, dtype: float64


from scipy.stats import pearsonr
sentiment_mapping = {
    'Positive': 1,
    'Neutral': 0,
    'Negative': -1,
}
df['Sentiment_numeric'] = df['Sentiment'].map(sentiment_mapping)

correlation_coefficient, _ = pearsonr(df['Review Length'], df['Sentiment_numeric'])

print(f"Correlation Coefficient: {correlation_coefficient}")

Correlation Coefficient: -0.3256368670501089


restaurant_with_highest_votes = df.nlargest(1, 'Votes')
restaurant_with_lowest_votes = df.nsmallest(1, 'Votes')

result_df = pd.DataFrame({
    'Restaurant with High Votes': restaurant_with_highest_votes.values[0],
    'Restaurant with Low Votes': restaurant_with_lowest_votes.values[0]
}, index=df.columns)
result_df


highest_votes_restaurant = df.loc[df['Votes'].idxmax()]
lowest_votes_restaurant = df.loc[df['Votes'].idxmin()]
print("Restaurant with the highest number of Votes:")
print(highest_votes_restaurant[["Restaurant Name", "Votes", "Aggregate rating"]])
print(" \n Restaurant with the lowest number of Votes:")
print(lowest_votes_restaurant[["Restaurant Name", "Votes", "Aggregate rating"]])

Restaurant with the highest number of Votes:
Restaurant Name      Toit
Votes               10934
Aggregate rating      4.8
Name: 728, dtype: object
 
 Restaurant with the lowest number of Votes:
Restaurant Name     Cantinho da Gula
Votes                              0
Aggregate rating                 0.0
Name: 69, dtype: object


plt.figure(figsize=(10,6))
sns.scatterplot(x='Votes', y = 'Aggregate rating', data=df)
plt.title("Correlation between Number of Votes and Restaurant Rating")
plt.xlabel("Number of Votes")
plt.ylabel("Aggregate rating")
plt.show()

Correlation_coefficient= df['Votes'].corr(df['Aggregate rating'])
print(f" \n Correlation Coefficent between Votes and Rating: {correlation_coefficient}")

 
 Correlation Coefficent between Votes and Rating: -0.3256368670501089


votes_rating_analysis = df['Aggregate rating'].corr(df['Votes'])
print("Correlation between Aggregate rating and Votes:", votes_rating_analysis)

Correlation between Aggregate rating and Votes: 0.3136905841954117


corr_matrix = df.select_dtypes(["int64", "float64"]).corr()
plt.figure(figsize=(12, 8))
sns.heatmap(corr_matrix, annot=True, cmap='YlGnBu', fmt=".2f")
plt.title("Correlation Heatmap for Numerical Columns")
plt.show()


grouped_data = df.groupby(['Price range', 'Has Online delivery']).size().unstack()

colors = ['green', 'red']
ax = grouped_data.plot(kind='bar', color=colors, width=0.8)
plt.xlabel('Price Range')
plt.ylabel('Count')
plt.title('Distribution of Online Delivery by Price Range')
plt.xticks(rotation=0)
plt.legend(title='Has Online delivery')
plt.show()


grouped_data = df.groupby(['Price range', 'Has Table booking']).size().unstack()

colors = ['green', 'red']
ax = grouped_data.plot(kind='bar', color=colors, width=0.8)
plt.xlabel('Price Range')
plt.ylabel('Count')
plt.title('Distribution of Table booking by Price Range')
plt.xticks(rotation=0)
plt.legend(title='Has Table booking')
plt.show()


grouped_data = df.groupby('Price range').agg(
    Online_delivery_percentage=('Has Online delivery', lambda x: (x == 'Yes').mean() * 100),
    Table_booking_percentage=('Has Table booking', lambda x: (x == 'Yes').mean() * 100),
)

# Plot
ax = grouped_data.plot(kind='bar', figsize=(8, 6))
plt.xlabel('Price Range')
plt.ylabel('Percentage')
plt.title('Percentage of Restaurants Offering Services by Price Range')
plt.xticks(rotation=0)
plt.legend(title='Service')
plt.show()


from scipy.stats import chi2_contingency
#Online Delivery
price_online_contingency = pd.crosstab(df['Price range'], df['Has Online delivery'])

chi2, p, _, _ = chi2_contingency(price_online_contingency)
alpha = 0.05
if p < alpha:
    print("There is a statistically significant association between Price range and Online delivery.")
else:
    print("There is no statistically significant association between Price range and Online delivery.")

#Table booking
price_table_booking_contingency = pd.crosstab(df['Price range'], df['Has Table booking'])
chi2, p, _, _ = chi2_contingency(price_table_booking_contingency)

if p < alpha:
    print("There is a statistically significant association between Price range and Table booking.")
else:
    print("There is no statistically significant association between Price range and Table booking.")

There is a statistically significant association between Price range and Online delivery.
There is a statistically significant association between Price range and Table booking.

	Restaurant ID	Restaurant Name	Country Code	City	Address	Locality	Locality Verbose	Longitude	Latitude	Cuisines	...	Currency	Has Table booking	Has Online delivery	Is delivering now	Switch to order menu	Price range	Aggregate rating	Rating color	Rating text	Votes
0	6317637	Le Petit Souffle	162	Makati City	Third Floor, Century City Mall, Kalayaan Avenu...	Century City Mall, Poblacion, Makati City	Century City Mall, Poblacion, Makati City, Mak...	121.027535	14.565443	French, Japanese, Desserts	...	Botswana Pula(P)	Yes	No	No	No	3	4.8	Dark Green	Excellent	314
1	6304287	Izakaya Kikufuji	162	Makati City	Little Tokyo, 2277 Chino Roces Avenue, Legaspi...	Little Tokyo, Legaspi Village, Makati City	Little Tokyo, Legaspi Village, Makati City, Ma...	121.014101	14.553708	Japanese	...	Botswana Pula(P)	Yes	No	No	No	3	4.5	Dark Green	Excellent	591
2	6300002	Heat - Edsa Shangri-La	162	Mandaluyong City	Edsa Shangri-La, 1 Garden Way, Ortigas, Mandal...	Edsa Shangri-La, Ortigas, Mandaluyong City	Edsa Shangri-La, Ortigas, Mandaluyong City, Ma...	121.056831	14.581404	Seafood, Asian, Filipino, Indian	...	Botswana Pula(P)	Yes	No	No	No	4	4.4	Green	Very Good	270
3	6318506	Ooma	162	Mandaluyong City	Third Floor, Mega Fashion Hall, SM Megamall, O...	SM Megamall, Ortigas, Mandaluyong City	SM Megamall, Ortigas, Mandaluyong City, Mandal...	121.056475	14.585318	Japanese, Sushi	...	Botswana Pula(P)	No	No	No	No	4	4.9	Dark Green	Excellent	365
4	6314302	Sambo Kojin	162	Mandaluyong City	Third Floor, Mega Atrium, SM Megamall, Ortigas...	SM Megamall, Ortigas, Mandaluyong City	SM Megamall, Ortigas, Mandaluyong City, Mandal...	121.057508	14.584450	Japanese, Korean	...	Botswana Pula(P)	Yes	No	No	No	4	4.8	Dark Green	Excellent	229
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
9546	5915730	Naml۱ Gurme	208	��stanbul	Kemanke�� Karamustafa Pa��a Mahallesi, R۱ht۱m ...	Karak�_y	Karak�_y, ��stanbul	28.977392	41.022793	Turkish	...	Turkish Lira(TL)	No	No	No	No	3	4.1	Green	Very Good	788
9547	5908749	Ceviz A��ac۱	208	��stanbul	Ko��uyolu Mahallesi, Muhittin ��st�_nda�� Cadd...	Ko��uyolu	Ko��uyolu, ��stanbul	29.041297	41.009847	World Cuisine, Patisserie, Cafe	...	Turkish Lira(TL)	No	No	No	No	3	4.2	Green	Very Good	1034
9548	5915807	Huqqa	208	��stanbul	Kuru�_e��me Mahallesi, Muallim Naci Caddesi, N...	Kuru�_e��me	Kuru�_e��me, ��stanbul	29.034640	41.055817	Italian, World Cuisine	...	Turkish Lira(TL)	No	No	No	No	4	3.7	Yellow	Good	661
9549	5916112	A��k Kahve	208	��stanbul	Kuru�_e��me Mahallesi, Muallim Naci Caddesi, N...	Kuru�_e��me	Kuru�_e��me, ��stanbul	29.036019	41.057979	Restaurant Cafe	...	Turkish Lira(TL)	No	No	No	No	4	4.0	Green	Very Good	901
9550	5927402	Walter's Coffee Roastery	208	��stanbul	Cafea��a Mahallesi, Bademalt۱ Sokak, No 21/B, ...	Moda	Moda, ��stanbul	29.026016	40.984776	Cafe	...	Turkish Lira(TL)	No	No	No	No	2	4.0	Green	Very Good	591

COGNIFYZ TECHNOLOGIES: RESTAURANT ANALYSIS¶

LEVEL 1 - TASK 1 - TOP CUISINES¶

Question: Determine the top three most common cuisines in the dataset¶

Question: Calculate the percentage of restaurants that serve each of the top cuisines¶

LEVEL 1 TASK 2 - CITY ANALYSIS¶

Question: Identify the city with the highest number of Restaurants in the dataset¶

Question: Calculate the average rating for restaurants in each city¶

Question: Determine the city with the highest average rating¶

LEVEL 1 - TASK 3 - PRICE RANGE DISTRIBUTION¶

Question: Create a Histogram or Bar Chart to visulaize the distribution of price ranges among the restuarants¶

Question: Calculate the percentage of restaurants in each price range category¶

LEVEL 1 - TASK 4 - ONLINE DELIVERY¶

Question: Determine the percentage of restaurants that offer online delivery¶

Question: Compare the average ratings of restuarants with and without online delivery¶

LEVEL 2 - TASK 1 - RESTAURANT RATINGS¶

Question: Analyze the distribution of aggregate ratings and determine the most common rating range¶

Question: Calculate the average number of votes received by restaurants¶

LEVEL 2 - TASK 2 - CUISINE COMBINATION¶

Question: Identify the most common combinations of cuisines in the dataset¶

Question: Determine if certain cuisine combinations tend to have higher ratings¶

LEVEL 2 - TASK 3 - GEOGRAPHIC ANALYSIS¶

Question: Plot the locations of restaurants on a map using longitude and latitude coordinates¶

Question: Identify any patterns of clusters of restaurants in specific areas¶

LEVEL 2 - TASK 4 - RESTAURANT CHAINS¶

Question: Identify if there are any restaurant chains present in the dataset¶

Question: Analyze the ratings and popularity of different restaurant chains¶

LEVEL 3 - TASK 1 - RESTAURANT REVIEWS¶

Question: Analyze the text reviews to identify the most common positive and negative keywords¶

Question: Calculate the average length of reviews and explore if there is a relationship between review length and rating¶

LEVEL 3 - TASK 2 - VOTES ANALYSIS¶

Question: Identify the Restaurants with highest and lowest number of votes¶

Question: Analyze if there is a correlation between the number of votes and the rating of a restuarant¶

LEVEL 3 - TASK 3 - PRICE RANGE VS. ONLINE DELIVERY AND TABLE BOOKING¶

Question: Analyze if there is a relationship between the price range and the availability of online delivery and table booking¶

Question: Determine if higher-priced restaurants are more likely to offer these services¶

	Restaurant with High Votes	Restaurant with Low Votes
Restaurant ID	51705	6710645
Restaurant Name	Toit	Cantinho da Gula
Country Code	1	30
City	Bangalore	S��o Paulo
Address	298, Namma Metro Pillar 62, 100 Feet Road, Ind...	Rua Pedroso Alvarenga, 522, Itaim Bibi, S��o P...
Locality	Indiranagar	Itaim Bibi
Locality Verbose	Indiranagar, Bangalore	Itaim Bibi, S��o Paulo
Longitude	77.640709	-46.675667
Latitude	12.979166	-23.581
Cuisines	Italian, American, Pizza	Brazilian
Average Cost for two	2000	55
Currency	Indian Rupees(Rs.)	Brazilian Real(R$)
Has Table booking	No	No
Has Online delivery	No	No
Is delivering now	No	No
Switch to order menu	No	No
Price range	4	2
Aggregate rating	4.8	0.0
Rating color	Dark Green	White
Rating text	Excellent	Not rated
Votes	10934	0
Sentiment	Positive	Neutral
Review Length	9	9
Sentiment_numeric	1	0